4min chapter

Lex Fridman Podcast cover image

#118 – Grant Sanderson: Math, Manim, Neural Networks & Teaching with 3Blue1Brown

Lex Fridman Podcast

CHAPTER

Using a Dumb Gradient Decayment Algorithm to Find Really Good Solutions

A dumb gradient descent algorithm is able to find really good solutions. It's not terribly surprising that you have these interesting points that exist when you make your space so high dimensional like gpt three what did it have 175 billion parameters yeah. The reason the gradient descent works well with neural networks and not just you know choose however you want to parameterize this space  is that that layered structure lets you decompose the derivative in a way that makes it computationally feasible.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode